• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.50-63
• /
• 1995

In this paper, we propose a face recognition method using a neuro-fuzzy algorithm. In the preprocessing step, we extract the face part from the background image by tracking face boundaries. Then based on the a priori knowledge of human faces we extract the features such as widths of eyes and mouth, and distances from eye to nose and nose to mouth. In the recognition step. We use a neuro-fuzzy algorithm that employs a fuzzy membership function and modified error backpropagation algorithm. The former absorbs the variation of feature values and the latter shows good learning efficiency. Computer simulation results with 20 persons show that the proposed method gives higher recognition rate than the conventional ones.

• Communications for Statistical Applications and Methods
• /
• v.27 no.2
• /
• pp.255-268
• /
• 2020

A mixture of multivariate canonical fundamental skew t-distribution (CFUST) has been of interest in various fields. In particular, interest in the unsupervised learning society is noteworthy. However, fitting the model via EM algorithm suffers from significant processing time. The main cause is due to the calculation of many multivariate t-cdfs (cumulative distribution functions) in E-step. In this article, we provide an approximate, but fast calculation method for the in univariate fashion, which is the product of successively conditional univariate t-cdfs with Taylor's first order approximation. By replacing all multivariate t-cdfs in E-step with the proposed approximate versions, we obtain the admissible results of fitting the model, where it gives 85% reduction time for the 5 dimensional skewness case of the Australian Institution Sport data set. For this approach, discussions about rough properties, advantages and limits are also presented.

• ETRI Journal
• /
• v.41 no.3
• /
• pp.298-307
• /
• 2019

This paper investigates the use of the inverse-free sparse Bayesian learning (SBL) approach for peak-to-average power ratio (PAPR) reduction in orthogonal frequency-division multiplexing (OFDM)-based multiuser massive multiple-input multiple-output (MIMO) systems. The Bayesian inference method employs a truncated Gaussian mixture prior for the sought-after low-PAPR signal. To learn the prior signal, associated hyperparameters and underlying statistical parameters, we use the variational expectation-maximization (EM) iterative algorithm. The matrix inversion involved in the expectation step (E-step) is averted by invoking a relaxed evidence lower bound (relaxed-ELBO). The resulting inverse-free SBL algorithm has a much lower complexity than the standard SBL algorithm. Numerical experiments confirm the substantial improvement over existing methods in terms of PAPR reduction for different MIMO configurations.

• Genomics & Informatics
• /
• v.21 no.1
• /
• pp.15.1-15.4
• /
• 2023

Bioinformatics education can be defined as the teaching and learning of how to use software tools, along with mathematical and statistical analysis, to solve biological problems. Although many resources are available, most students still struggle to understand even the simplest sequence alignment algorithms. Applying visualizations to these topics benefits both lecturers and students. Unfortunately, educational software for visualizing step-by-step processes in the user experience of sequence alignment algorithms is rare. In this article, an educational visualization tool for biological sequence alignment is presented, and the source code is released in order to encourage the collaborative power of open-source software, with the expectation of further contributions from the community in the future. Two different modules are integrated to enable a student to investigate the characteristics of alignment algorithms.

• The Journal of Korean Association of Computer Education
• /
• v.9 no.5
• /
• pp.53-64
• /
• 2006

This paper proposes show how to support the field-learning by using web and mobile system. This Web Mobile system is to help the users plan, carry out and evaluate a field learning. Usually the field-learning is going through three steps: preparation, actual field activity and post-evaluation activity. The proposing Web-Mobile system supports an integrated methodology to more effectively help, lead and manage this three step field-learning, This effective approach will help the learners develop their creativity, self-control and partnership to each other.

• Korean Journal of Child Studies
• /
• v.28 no.5
• /
• pp.253-267
• /
• 2007

This study examined the relationships between multiple intelligences as cognitive factors and affective factors of learning motivation and academic self-concept. The data were collected from 276 4th grade elementary school students and analyzed by correlation, multi-variate analysis, and step-wise multiple regression. Results were that (1) multiple intelligences, learning motivation, and academic self-concept had statistically significant correlations among themselves. Multi-variate analysis showed that intra-personal intelligence explained 58.6% of the linear combination of learning motivation and academic self-concept. (2) Intra-personal intelligence explained 29% to 58% of learning motivation and its sub-factors of achievement motivation, internal locus of control, self-efficacy, and self-regulation. (3) Intra-personal intelligence, logical-mathematical intelligence, musical intelligence, and inter-personal intelligence were explanatory variables for academic self-concept and its sub-factors.

• Journal of The Korean Association For Science Education
• /
• v.39 no.1
• /
• pp.35-44
• /
• 2019

Currently, most of the science and engineering students who enter the university are required to take general chemistry and general chemistry experimental subjects. However they have different learning bases about learning basic science subjects. Regarding college entrance examinations, the current system is used for selection, so they have different levels of basic knowledge. But, without considering this situation, all of the students in science and engineering are participating in the same basic science class, some learners are relatively easy to adapt to learning, while others experience extreme difficulties and suddenly give up. This is true. The purpose of this study is to develop a scale to measure the ability to learn general chemistry of freshmen in science and engineering at H University in the Seoul Metropolitan area and to analyze what kind of learning backgrounds are related to learners. The results show that gender and major are not related to general chemistry learning major, and it we found that there is a close relationship to the relationship between their major and chemistry, the level of the chemistry learning in the high school, and the selection of chemistry in college entrance examinations. In addition, it was found that the degree of feeling that pre-learning is beneficial to current learning and that it is common with current learning is also a factor related to general chemistry learning aptitude. Therefore, in this study, we propose two ways of presenting and promoting a guide for learning by majors, and establishing a step-by-step learning system considering the level of students.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.1 no.1
• /
• pp.125-130
• /
• 2001

In this paper, we propose a new type of evolution strategies combined with reinforcement learning. We use the variances of fitness occurred by mutation to make the reinforcement signals which estimate and control the step length of mutation. With this proposed method, the convergence rate is improved. Also, we use cauchy distributed mutation to increase global convergence faculty. Cauchy distributed mutation is more likely to escape from a local minimum or move away from a plateau. After an outline of the history of evolution strategies, it is explained how evolution strategies can be combined with the reinforcement learning, named reinforcement evolution strategies. The performance of proposed method will be estimated by comparison with conventional evolution strategies on several test problems.

• Journal of the Korean Society of Earth Science Education
• /
• v.4 no.3
• /
• pp.242-250
• /
• 2011

The present study compared the contents and methods of elementary science education in schools and education institutes for the gifted and surveyed the contents and methods of science education for the gifted desired by students in order to set the direction of elementary science education at education institutes for the gifted. For this study, we conducted interviews with a 5th-grade male student and a 6th-grade female student at the science class of the Education Institutes for the Gifted run by Iksan Education Office. Besides, printed materials were collected and used to refer to the contents of education. The results of this study are as follows. First, in school, the student learn according to the curriculum defined by the government and the contents begin with elementary and basic ones and move step by step to deeper and wider scientific principles. On the contrary, in the education institute for the gifted, the contents of teaching materials are decided at the teacher's discretion, and because they target gifted children, their level is higher than that of the science curriculum in school. Second, the most common teaching method in school is lecturing and, next, experiments, group activities, etc. On the contrary, in the education institute for the gifted, experiments are used most frequently, and various educational methods are adopted including lectures, project learning and cyber learning. Third, the contents of science education that gifted children wanted to learn are not limited to any specific area. Science education methods that gifted children wanted were various, including project learning, group activities, experiments, and report making and presentation.